SID.ir New Version

Paper Information

Journal:   MODARES JOURNAL OF ELECTRICAL ENGINEERING   FALL 2010 , Volume 10 , Number 3; Page(s) 55 To 70.
 
Paper: 

Nonlinear Modeling Of Speech Poincare Sections In Combination With Frequency Analysis To Improve Speech Recognition Performance

 
 
Author(s):  Jafari Ayoub*, Almasganj F., Nabi Bidhendi M.
 
* BIOMEDICAL ENGINEERING DEPARTMENT, ISLAMIC AZAD UNIVERSITY, QAZVIN BRANCH
 
Abstract: 
This paper introduces a novel approach to improve performance of speech recognition systems using a combination of features obtained from speech reconstructed phase space (RPS) and frequency domain analysis. By choosing an appropriate value for the dimension, reconstructed phase space is assured to be topologically equivalent to the dynamics of the speech production system, and could therefore include information that may be absent in analysis approaches based on linear methods. Also, complicated systems such as speech production system can present cyclic and oscillatory patterns and Poincare sections could be used as an effective tool in analysis of such trajectories. In this research, a statistical modeling approach based on Gaussian Mixture models (GMM) was applied to the Poincare sections of speech RPS. The final feature set is obtained from a feature selection stage among parameters of GMM model and the usual Mel Frequency Cepstral coefficients (MFCC). An HMM-based speech recognition system and the TIMIT speech database are used to evaluate performance of the proposed feature extraction system for isolated and continuous speech recognition. Experiments represent about 5.7% absolute isolated phoneme recognition accuracy improvements in isolated phoneme recognition performance. The new approach is shown to be a viable and effective alternative to traditional feature extraction methods, particularly for signals such as speech with strong nonlinear characteristics.
 
Keyword(s): RECONSTRUCTED PHASE SPACE (RPS), POINCARE SECTIONS, SPEECH RECOGNITION, FEATURE EXTRACTION, NON-LINEAR MODELING
 
 
International related papers: 
 
Most related Highly related Moderately related Least related
 
References: 
  • Not Registered.
  •  
  •  
 
Citations: 
  • Not Registered.
 
+ Click to Cite.
APA: Copy

JAFARI, A., & ALMASGANJ, F., & NABI BIDHENDI, M. (2010). NONLINEAR MODELING OF SPEECH POINCARE SECTIONS IN COMBINATION WITH FREQUENCY ANALYSIS TO IMPROVE SPEECH RECOGNITION PERFORMANCE. MODARES JOURNAL OF ELECTRICAL ENGINEERING, 10(3), 55-70. https://www.sid.ir/en/journal/ViewPaper.aspx?id=193063



Vancouver: Copy

JAFARI AYOUB, ALMASGANJ F., NABI BIDHENDI M.. NONLINEAR MODELING OF SPEECH POINCARE SECTIONS IN COMBINATION WITH FREQUENCY ANALYSIS TO IMPROVE SPEECH RECOGNITION PERFORMANCE. MODARES JOURNAL OF ELECTRICAL ENGINEERING. 2010 [cited 2022August20];10(3):55-70. Available from: https://www.sid.ir/en/journal/ViewPaper.aspx?id=193063



IEEE: Copy

JAFARI, A., ALMASGANJ, F., NABI BIDHENDI, M., 2010. NONLINEAR MODELING OF SPEECH POINCARE SECTIONS IN COMBINATION WITH FREQUENCY ANALYSIS TO IMPROVE SPEECH RECOGNITION PERFORMANCE. MODARES JOURNAL OF ELECTRICAL ENGINEERING, [online] 10(3), pp.55-70. Available: https://www.sid.ir/en/journal/ViewPaper.aspx?id=193063.



 
 
Persian Abstract Yearly Visit 47
 
 
Latest on Blog
Enter SID Blog